System for modeling 3D scene from single design picture

Abstract

The invention relates to the technical field of computer vision, in particular to a system for modeling a 3D scene from a single design picture. The method comprises the following steps: rendering: randomly arranging objects in a rendering engine to obtain a rendering result graph and a data set of a 3D object transformation matrix of each object; model extraction: extracting a prediction model from the data set by using a deep learning network; instance segmentation: inputting a single scene design picture, and predicting an instance segmentation result and a transformation matrix of a 3D object of each instance; and modeling: placing an object corresponding to a single instance in a scene under the guidance of the transformation matrix to complete result modeling. According to the method, instance segmentation is performed by using the deep neural network MaskR-CNN to obtain the images of a 2D object bounding box and a bounding box area, and the 3D scene arrangement is automatically completed by a single design picture according to the 2D plane mapping of the 3D object corresponding to the instance segmentation result, so that the scene construction time can be greatly shortened, and the scene construction speed is increased.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a system for modeling a 3D scene from a single design picture. Background technique [0002] 3D modeling is widely used in construction, home improvement, virtual city, ARVR, 3D games and other fields. Putting the model into the rendering engine can render 3D images offline or in fact. Arranging the model in the scene to form the entire scene material is called building the scene, which is generally constructed by 3D artists using 3D modeling software. The construction of the scene has a very important impact on the overall final rendering effect. [0003] However, the traditional scene construction method requires a lot of communication and manual adjustments to polish a scene. The UI designer is required to first produce a single scene design drawing (2D), and then the 3D artist makes the layout of the 3D scene according to the design drawing. No matter in terms of ...

AI Technical Summary

Problems solved by technology

And for another application scene, although the previous object materials can be reused, the scene still needs to be rearranged, which is a waste of time

Images